Upload 6 files

README.md

@@ -0,0 +1,77 @@
+---
+tags:
+- audio-classification
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- f1
+model-index:
+- name: wavlm-base
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wavlm-base
+
+This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on the galsenai/waxal_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1345
+- Accuracy: 0.6783
+- Precision: 0.8774
+- F1: 0.7615
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 30
+- eval_batch_size: 30
+- seed: 0
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 120
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 32.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
+| 4.4506        | 2.53  | 500  | 4.8601          | 0.0224   | 0.0136    | 0.0066 |
+| 3.0523        | 5.05  | 1000 | 4.6674          | 0.0720   | 0.0460    | 0.0394 |
+| 1.949         | 7.58  | 1500 | 4.1533          | 0.1156   | 0.1847    | 0.1064 |
+| 1.3427        | 10.1  | 2000 | 3.8173          | 0.1448   | 0.2382    | 0.1347 |
+| 1.0064        | 12.63 | 2500 | 3.5546          | 0.2183   | 0.4464    | 0.2385 |
+| 0.7985        | 15.15 | 3000 | 3.1172          | 0.3842   | 0.6336    | 0.4258 |
+| 0.6505        | 17.68 | 3500 | 2.9231          | 0.5165   | 0.7677    | 0.5995 |
+| 0.5367        | 20.2  | 4000 | 2.4935          | 0.5961   | 0.8182    | 0.6755 |
+| 0.465         | 22.73 | 4500 | 2.2411          | 0.6412   | 0.8624    | 0.7272 |
+| 0.4075        | 25.25 | 5000 | 2.1345          | 0.6783   | 0.8774    | 0.7615 |
+| 0.3793        | 27.78 | 5500 | 2.2535          | 0.6681   | 0.8792    | 0.7543 |
+| 0.3418        | 30.3  | 6000 | 2.3390          | 0.6662   | 0.8905    | 0.7576 |
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.9.1.dev0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 32.0,
+    "eval_accuracy": 0.6782872300113679,
+    "eval_f1": 0.76152721933526,
+    "eval_loss": 2.134546995162964,
+    "eval_precision": 0.8773557553113618,
+    "eval_runtime": 70.2134,
+    "eval_samples_per_second": 37.585,
+    "eval_steps_per_second": 1.253,
+    "train_loss": 1.2320244793940072,
+    "train_runtime": 19932.9865,
+    "train_samples_per_second": 38.125,
+    "train_steps_per_second": 0.318
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 32.0,
+    "eval_accuracy": 0.6782872300113679,
+    "eval_f1": 0.76152721933526,
+    "eval_loss": 2.134546995162964,
+    "eval_precision": 0.8773557553113618,
+    "eval_runtime": 70.2134,
+    "eval_samples_per_second": 37.585,
+    "eval_steps_per_second": 1.253
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 32.0,
+    "train_loss": 1.2320244793940072,
+    "train_runtime": 19932.9865,
+    "train_samples_per_second": 38.125,
+    "train_steps_per_second": 0.318
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 0.6782872300113679,
+  "best_model_checkpoint": "wavlm-base/checkpoint-5000",
+  "epoch": 32.0,
+  "global_step": 6336,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.3659305993690853e-05,
+      "loss": 4.4506,
+      "step": 500
+    },
+    {
+      "epoch": 2.53,
+      "eval_accuracy": 0.02235695339143615,
+      "eval_f1": 0.006616186351103852,
+      "eval_loss": 4.86008358001709,
+      "eval_precision": 0.013553337387865622,
+      "eval_runtime": 71.9324,
+      "eval_samples_per_second": 36.687,
+      "eval_steps_per_second": 1.223,
+      "step": 500
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 2.8074359873728517e-05,
+      "loss": 3.0523,
+      "step": 1000
+    },
+    {
+      "epoch": 5.05,
+      "eval_accuracy": 0.07199696854869268,
+      "eval_f1": 0.03943960465213343,
+      "eval_loss": 4.667360305786133,
+      "eval_precision": 0.0460329111931258,
+      "eval_runtime": 71.0687,
+      "eval_samples_per_second": 37.133,
+      "eval_steps_per_second": 1.238,
+      "step": 1000
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 2.5443703963521573e-05,
+      "loss": 1.949,
+      "step": 1500
+    },
+    {
+      "epoch": 7.58,
+      "eval_accuracy": 0.11557408109132247,
+      "eval_f1": 0.10642928153043356,
+      "eval_loss": 4.153301239013672,
+      "eval_precision": 0.18473852089235457,
+      "eval_runtime": 71.0445,
+      "eval_samples_per_second": 37.146,
+      "eval_steps_per_second": 1.239,
+      "step": 1500
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 2.2813048053314627e-05,
+      "loss": 1.3427,
+      "step": 2000
+    },
+    {
+      "epoch": 10.1,
+      "eval_accuracy": 0.14475179992421372,
+      "eval_f1": 0.1346763066246049,
+      "eval_loss": 3.8172836303710938,
+      "eval_precision": 0.23822785193835883,
+      "eval_runtime": 74.8027,
+      "eval_samples_per_second": 35.279,
+      "eval_steps_per_second": 1.176,
+      "step": 2000
+    },
+    {
+      "epoch": 12.63,
+      "learning_rate": 2.0182392143107683e-05,
+      "loss": 1.0064,
+      "step": 2500
+    },
+    {
+      "epoch": 12.63,
+      "eval_accuracy": 0.2182644941265631,
+      "eval_f1": 0.23851786199348127,
+      "eval_loss": 3.5546185970306396,
+      "eval_precision": 0.44639974594463316,
+      "eval_runtime": 71.1082,
+      "eval_samples_per_second": 37.112,
+      "eval_steps_per_second": 1.238,
+      "step": 2500
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 1.7551736232900737e-05,
+      "loss": 0.7985,
+      "step": 3000
+    },
+    {
+      "epoch": 15.15,
+      "eval_accuracy": 0.3842364532019704,
+      "eval_f1": 0.4258289880546809,
+      "eval_loss": 3.117234230041504,
+      "eval_precision": 0.6336488091054493,
+      "eval_runtime": 70.3629,
+      "eval_samples_per_second": 37.506,
+      "eval_steps_per_second": 1.251,
+      "step": 3000
+    },
+    {
+      "epoch": 17.68,
+      "learning_rate": 1.4921080322693792e-05,
+      "loss": 0.6505,
+      "step": 3500
+    },
+    {
+      "epoch": 17.68,
+      "eval_accuracy": 0.5164835164835165,
+      "eval_f1": 0.5994643376487049,
+      "eval_loss": 2.9230926036834717,
+      "eval_precision": 0.7677367523432096,
+      "eval_runtime": 70.3236,
+      "eval_samples_per_second": 37.527,
+      "eval_steps_per_second": 1.251,
+      "step": 3500
+    },
+    {
+      "epoch": 20.2,
+      "learning_rate": 1.2290424412486847e-05,
+      "loss": 0.5367,
+      "step": 4000
+    },
+    {
+      "epoch": 20.2,
+      "eval_accuracy": 0.5960591133004927,
+      "eval_f1": 0.6755266051820856,
+      "eval_loss": 2.4934628009796143,
+      "eval_precision": 0.818165400699518,
+      "eval_runtime": 69.6955,
+      "eval_samples_per_second": 37.865,
+      "eval_steps_per_second": 1.263,
+      "step": 4000
+    },
+    {
+      "epoch": 22.73,
+      "learning_rate": 9.659768502279902e-06,
+      "loss": 0.465,
+      "step": 4500
+    },
+    {
+      "epoch": 22.73,
+      "eval_accuracy": 0.6411519514967791,
+      "eval_f1": 0.7272288000165434,
+      "eval_loss": 2.241117238998413,
+      "eval_precision": 0.86241474957474,
+      "eval_runtime": 70.29,
+      "eval_samples_per_second": 37.544,
+      "eval_steps_per_second": 1.252,
+      "step": 4500
+    },
+    {
+      "epoch": 25.25,
+      "learning_rate": 7.029112592072957e-06,
+      "loss": 0.4075,
+      "step": 5000
+    },
+    {
+      "epoch": 25.25,
+      "eval_accuracy": 0.6782872300113679,
+      "eval_f1": 0.76152721933526,
+      "eval_loss": 2.134546995162964,
+      "eval_precision": 0.8773557553113618,
+      "eval_runtime": 70.2432,
+      "eval_samples_per_second": 37.569,
+      "eval_steps_per_second": 1.253,
+      "step": 5000
+    },
+    {
+      "epoch": 27.78,
+      "learning_rate": 4.398456681866012e-06,
+      "loss": 0.3793,
+      "step": 5500
+    },
+    {
+      "epoch": 27.78,
+      "eval_accuracy": 0.6680560818491853,
+      "eval_f1": 0.7542953137768733,
+      "eval_loss": 2.2534902095794678,
+      "eval_precision": 0.8791790950841867,
+      "eval_runtime": 70.1811,
+      "eval_samples_per_second": 37.603,
+      "eval_steps_per_second": 1.254,
+      "step": 5500
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 1.767800771659067e-06,
+      "loss": 0.3418,
+      "step": 6000
+    },
+    {
+      "epoch": 30.3,
+      "eval_accuracy": 0.6661614247821145,
+      "eval_f1": 0.7575999245015367,
+      "eval_loss": 2.3390462398529053,
+      "eval_precision": 0.8904662594400684,
+      "eval_runtime": 70.3334,
+      "eval_samples_per_second": 37.521,
+      "eval_steps_per_second": 1.251,
+      "step": 6000
+    },
+    {
+      "epoch": 32.0,
+      "step": 6336,
+      "total_flos": 3.804690514724178e+19,
+      "train_loss": 1.2320244793940072,
+      "train_runtime": 19932.9865,
+      "train_samples_per_second": 38.125,
+      "train_steps_per_second": 0.318
+    }
+  ],
+  "max_steps": 6336,
+  "num_train_epochs": 32,
+  "total_flos": 3.804690514724178e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d78303a058fc6cb98946f3d25ed93eee9a4848daff7fe0a1f307e959024839c
+size 3503